Backend Engineer focused on AI Agents, Memory & Context

About Vantum

Vantum helps fractional operators win new clients while delivering for the clients they already have. When you’re managing several engagements, client work can consume the week and leave little time to grow your own business. We’re building Vantum to help operators make progress on both.

At the center is Ask Vantum, an AI chat that understands their goals, connects to their work, and helps them decide what to do next. It needs to remember what matters and help users take action without making them explain themselves again.

We’re a team of five, working toward product-market fit. We’re looking for an engineer to build and improve the prompts, memory, context, and backend systems behind that experience.

You’ll work directly with the founders and help shape a core part of the product.

What you’ll own

Your primary focus is Ask Vantum’s chat harness: the code and instructions that connect the model to conversation history, memory, app data, and tools.

• System prompts and model behavior. Write, test, and refine the instructions that govern how Vantum responds, uses context, asks questions, and calls tools. Resolve conflicting instructions and make behavior consistent across different requests.

• Context management. Decide what the model needs each turn, what to retrieve, and what to leave out. Preserve important information as conversations grow.

• Memory. Separate lasting preferences from temporary instructions. Handle corrections, outdated information, and deletions so the assistant remembers accurately.

• Queries and retrieval. Pull relevant tasks, goals, calendar entries, notes, and documents. Choose the right retrieval approach for the question.

• Tool execution. Build actions that validate inputs, enforce permissions, and handle failures without creating duplicate work or claiming something happened when it didn’t.

• Reliability and evaluation. Trace bad responses, reproduce failures, and verify improvements. Monitor response quality, latency, and cost while keeping client information properly scoped.

Our stack: TypeScript, Next.js App Router, PostgreSQL, Prisma, and OpenRouter. We have an existing harness you’ll improve and extend.

What we’re looking for

You have strong backend fundamentals and are good at getting useful, reliable behavior from language models.

You should be able to:

• Write precise prompts. You’ve built system prompts and can explain how instructions, examples, tool descriptions, and output schemas affect behavior.

• Debug beyond the prompt. You can tell whether a bad response comes from unclear instructions, missing context, poor retrieval, a tool failure, or application code.

• Test your changes. You compare behavior across representative cases, track prompt versions, and check that fixing one problem hasn’t introduced another.

• Build solid backend systems. You write maintainable TypeScript, validated APIs, scoped database queries, and safe persistence changes.

• Show your work. You can walk through something you built, explain your decisions, and describe a failure you investigated.

• Communicate clearly in English. Precise writing matters in system prompts, technical discussions, and PRs.

• Take ownership. You clarify ambiguous work, flag blockers early, and carry a change through to verification.

Experience with chat systems, agent harnesses, memory, or retrieval is a strong advantage. A serious side project counts. Demonstrated ability matters more than years of experience, degrees, or employer names.

We want someone who follows developments in AI engineering and tests ideas critically. Tell us what you tried, what improved, and what you dropped because it wasn’t worth the complexity.

Why join

Ask Vantum is central to the product. Your work will directly affect whether users feel understood, trust the assistant, and return to it.

You’ll work closely with the founders, see feedback from real users, and have a say in how we solve problems. As you demonstrate your judgment and impact, there’s room to take on broader technical ownership.

We’re looking for curiosity, ambition, and follow-through. Someone who notices when the experience is wrong, wants to understand why, and cares enough to improve it.

A founder reviews architecture and sensitive production changes. You’ll have support while being expected to take responsibility for your work.

Compensation and working arrangements

• $1,200–$2,000 USD per month, depending on demonstrated ability.

• Full-time, remote position.

• At least four hours of weekday overlap with Bangkok (GMT+7).

• Potential for equity as the role develops.

How we hire

1. Screening call. We discuss your experience, work you’ve shipped, and what you’re looking for.

2. Repo and prep conversation. We share a repo and a problem to investigate. You’ll have the opportunity to ask questions, understand the existing system, and clarify the constraints.

3. Solution presentation. You present your diagnosis and proposed solution, including your reasoning, tradeoffs, and how you would verify the result.

AI tools are welcome. You should be able to explain your approach and adapt it as we discuss the problem.

Apply

Share something you personally built: a GitHub repo, PR, demo, or anonymized walkthrough.

Tell us what you owned and describe one chat, prompting, or backend failure you encountered: what went wrong, what you changed, and how you knew it worked.

Originally posted on Himalayas